Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    evokes meanings or qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    取的
    0.79
    드는
    0.68
    #(
    0.67
    Hvis
    0.64
    īj
    0.63
    Kako
    0.63
    Как
    0.61
    import
    0.61
     ome
    0.60
     προς
    0.59
    POSITIVE LOGITS
    тальян
    0.92
     fuerza
    0.83
     বিদ্যুৎ
    0.82
     szerző
    0.81
    ნდა
    0.80
    eared
    0.79
    teilung
    0.77
    ahoo
    0.77
     दर्शाता
    0.77
     aceptar
    0.77
    Act Density 0.003%

    No Known Activations